Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1330 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0006

Data Index: 393319 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0187. Min Act: -0.0006

Data Index: 754238 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1228897 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0164. Min Act: -0.0006

Data Index: 632464 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0169. Min Act: -0.0006

Data Index: 745147 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0166. Min Act: -0.0006

Data Index: 941560 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0160. Min Act: -0.0006

Data Index: 194218 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0159. Min Act: -0.0006

Data Index: 153418 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0163. Min Act: -0.0006

Data Index: 472509 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0163. Min Act: -0.0006

Data Index: 93942 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1647502 (Python Code)

Max Activating Token Index: 667

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1274854 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0150. Min Act: -0.0006

Data Index: 658399 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1233061 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0162. Min Act: -0.0006

Data Index: 140284 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0158. Min Act: -0.0006

Data Index: 497648 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1422294 (Python Code)

Max Activating Token Index: 942

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0147. Min Act: -0.0006

Data Index: 532736 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0157. Min Act: -0.0006

Data Index: 595323 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1093975 (C4 (Web Text))

Max Activating Token Index: 813